Share Email Print
cover

Proceedings Paper

Real time lobster posture estimation for behavior research
Author(s): Sheng Yan; Jo Arve Alfredsen
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In animal behavior research, the main task of observing the behavior of an animal is usually done manually. The measurement of the trajectory of an animal and its real-time posture description is often omitted due to the lack of automatic computer vision tools. Even though there are many publications for pose estimation, few are efficient enough to apply in real-time or can be used without the machine learning algorithm to train a classifier from mass samples. In this paper, we propose a novel strategy for the real-time lobster posture estimation to overcome those difficulties. In our proposed algorithm, we use the Gaussian mixture model (GMM) for lobster segmentation. Then the posture estimation is based on the distance transform and skeleton calculated from the segmentation. We tested the algorithm on a serials lobster videos in different size and lighting conditions. The results show that our proposed algorithm is efficient and robust under various conditions.

Paper Details

Date Published: 8 February 2017
PDF: 5 pages
Proc. SPIE 10225, Eighth International Conference on Graphic and Image Processing (ICGIP 2016), 102250F (8 February 2017); doi: 10.1117/12.2266430
Show Author Affiliations
Sheng Yan, Norwegian Univ. of Science and Technology (Norway)
Jo Arve Alfredsen, Norwegian Univ. of Science and Technology (Norway)


Published in SPIE Proceedings Vol. 10225:
Eighth International Conference on Graphic and Image Processing (ICGIP 2016)
Yulin Wang; Tuan D. Pham; Vit Vozenilek; David Zhang; Yi Xie, Editor(s)

© SPIE. Terms of Use
Back to Top